5 models, native protocol passthrough, billed per token. From 50% OFF of list price.
as of 2026-10-25
DeepSeek has two models on RouteMux, V4 Pro and V4.1 Flash. Both have a 1M-token context and up to 384K output tokens, think by default, and implement three real effort levels: low, high and max.
V4 Pro is the larger model of the V4 line, with 1.6T total and 49B active parameters and text-only input; it opened as a preview on April 24, 2026 and reached general availability on August 13, and the current build is 0813. V4.1 Flash (September 10) is the smallest model in DeepSeek's new architecture family, a 552B MoE with native vision; on October 17 DeepSeek upgraded it in place to the 1017 build under the same name. Pick V4 Pro when you want a fixed build for text-only work, and V4.1 Flash for images or speed.
DeepSeek has retired V4 Flash and V4 Flash Vision Exp; their names still work on RouteMux and are forwarded to V4.1 Flash.
Prepaid wallet billed on actual usage. No monthly fee, no minimum, credits never expire. The protocol layer is a native passthrough, not a translation shim: request bodies and SSE streaming match the official API, so clients only need a new base URL.
Every model is priced against the provider's published per-million-token rate at a fixed discount. Cache reads and writes use the same ratio, with no surcharge. The exact per-model rate is in the table above and always reflects current pricing.
Passed through. Request bodies, SSE streaming format, cache control and extended-thinking parameters match the upstream provider. Point your existing SDK at our base URL and the rest of your code stays unchanged.
No. The prepaid wallet is charged by actual token usage, with no monthly fee and no minimum spend. Unused balance can be refunded under our Terms of Service.